Home / Current Issue / Paper 1716179
Development of an Intelligent Location Data Clustering System Using Regular Expressions and DBSCAN
Subject area: Science,Engineering and Technology · Area of research: Machine Learning
DOI: https://doi.org/10.64388/IREV9I10-1716179
Abstract
Intelligent location data clustering systems are used to group spatial information such as GPS coordinates, addresses, and points of interest into meaningful clusters based on geographic proximity and similarity. In many developing countries, including Nigeria, the absence of a standardized address structure creates significant challenges for postal delivery, logistics management, emergency response, and urban planning. Address data often contain spelling variations, abbreviations, incomplete structures, and inconsistent formatting, making accurate geocoding and spatial analysis difficult. This study presents the development of an intelligent location data clustering system that integrates Regular Expressions (Regex) for address normalization and the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm for spatial clustering. The system preprocesses unstructured address data, standardizes them according to the Nigerian Postal Service (NIPOST) addressing framework, and groups similar addresses into spatial clusters. The approach eliminates reliance on external geocoding services and provides a locally controlled solution suitable for limited-resource environments. Experimental results demonstrate that the proposed system improves clustering accuracy and provides meaningful geographic groupings of address data. The system can be applied in postal delivery optimization, urban planning, logistics operations, and public service management.
Keywords
Location Data Clustering, Natural Language Processing (NLP), Regular Expressions, DBSCAN, Machine Learning, Address Standardization, NIPOST, Geospatial Analysis.
How to cite this paper
@article{1716179,
author = {Onyedikachukwu O. Ikechukwu-Onyenwe, Doris Asogwa, Ikechukwu Ekene Onyenwe},
title = {Development of an Intelligent Location Data Clustering System Using Regular Expressions and DBSCAN},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {10},
pages = {1515-1521},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1716179.pdf},
abstract = {Intelligent location data clustering systems are used to group spatial information such as GPS coordinates, addresses, and points of interest into meaningful clusters based on geographic proximity and similarity. In many developing countries, including Nigeria, the absence of a standardized address structure creates significant challenges for postal delivery, logistics management, emergency response, and urban planning. Address data often contain spelling variations, abbreviations, incomplete structures, and inconsistent formatting, making accurate geocoding and spatial analysis difficult. This study presents the development of an intelligent location data clustering system that integrates Regular Expressions (Regex) for address normalization and the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm for spatial clustering. The system preprocesses unstructured address data, standardizes them according to the Nigerian Postal Service (NIPOST) addressing framework, and groups similar addresses into spatial clusters. The approach eliminates reliance on external geocoding services and provides a locally controlled solution suitable for limited-resource environments. Experimental results demonstrate that the proposed system improves clustering accuracy and provides meaningful geographic groupings of address data. The system can be applied in postal delivery optimization, urban planning, logistics operations, and public service management.},
keywords = {Location Data Clustering, Natural Language Processing (NLP), Regular Expressions, DBSCAN, Machine Learning, Address Standardization, NIPOST, Geospatial Analysis.},
month = {April},
doi = {https://doi.org/10.64388/IREV9I10-1716179}
}